

Trenton Bricken
Researcher at Anthropic, specializing in mechanistic interpretability to understand how AI models work.
Top 3 podcasts with Trenton Bricken
Ranked by the Snipd community

2,434 snips
May 22, 2025 • 2h 24min
How Does Claude 4 Think? — Sholto Douglas & Trenton Bricken
In a fascinating conversation, Sholto Douglas, a reinforcement learning researcher at Anthropic, and Trenton Bricken, an expert in mechanistic interpretability, dive deep into the evolving landscape of AI. They discuss the latest advancements in reinforcement learning and the implications of AI achieving human-level tasks. The duo explores how to trace AI models' thought processes and the challenges of aligning AI with human values. They also address the future of AI in workplaces, emphasizing the need for individuals to adapt and engage with these transformative technologies.

904 snips
Mar 25, 2025 • 50min
AMA ft. Sholto & Trenton: New Book, Career Advice Given AGI, How I'd Start From Scratch
Join AI researchers Sholto Douglas and Trenton Bricken for an engaging discussion on the intricacies of artificial intelligence. They dive into the challenges AI faces in connecting ideas and the implications for tech careers. Sholto reveals insights from his new book on AI’s evolution, while Trenton shares unique career advice inspired by AGI. The conversation meanders through humorous takes on podcast guest selection, and the qualities needed to lead an AI lab, all served with a side of beard maintenance tips!

523 snips
Mar 28, 2024 • 3h 12min
Sholto Douglas & Trenton Bricken - How to Build & Understand GPT-7's Mind
Join AI researchers Sholto Douglas, known for his contributions to large language models, and Trenton Bricken from Anthropic, as they dive deep into the mind of GPT-7. They discuss how long context links can enhance AI's capabilities and explore the complexities of memory, reasoning, and the nature of intelligence in both humans and machines. The pair also tackles the challenges of AI alignment, potential superintelligence, and the importance of interpretability, all while sharing personal journeys through the quickly evolving landscape of AI.